mirror of https://git.ffmpeg.org/ffmpeg.git
50e194e6e1
For example, given TensorFlow model file espcn.pb, to generate native model file espcn.model, just run: python convert.py espcn.pb In current implementation, the native model file is generated for specific dnn network with hard-code python scripts maintained out of ffmpeg. For example, srcnn network used by vf_sr is generated with https://github.com/HighVoltageRocknRoll/sr/blob/master/generate_header_and_model.py#L85 In this patch, the script is designed as a general solution which converts general TensorFlow model .pb file into .model file. The script now has some tricky to be compatible with current implemention, will be refined step by step. The script is also added into ffmpeg source tree. It is expected there will be many more patches and community needs the ownership of it. Another technical direction is to do the conversion in c/c++ code within ffmpeg source tree. While .pb file is organized with protocol buffers, it is not easy to do such work with tiny c/c++ code, see more discussion at http://ffmpeg.org/pipermail/ffmpeg-devel/2019-May/244496.html. So, choose the python script. Signed-off-by: Guo, Yejun <yejun.guo@intel.com> |
||
---|---|---|
.. | ||
python | ||
.gitignore | ||
Makefile | ||
aviocat.c | ||
bisect-create | ||
bookmarklets.html | ||
cl2c | ||
clean-diff | ||
coverity.c | ||
crypto_bench.c | ||
cws2fws.c | ||
dvd2concat | ||
enum_options.c | ||
ffescape.c | ||
ffeval.c | ||
ffhash.c | ||
fourcc2pixfmt.c | ||
gen-rc | ||
graph2dot.c | ||
ismindex.c | ||
libav-merge-next-commit | ||
loudnorm.rb | ||
make_chlayout_test | ||
missing_codec_desc | ||
murge | ||
normalize.py | ||
patcheck | ||
pktdumper.c | ||
plotframes | ||
probetest.c | ||
qt-faststart.c | ||
seek_print.c | ||
sidxindex.c | ||
sofa2wavs.c | ||
target_dec_fate.list | ||
target_dec_fate.sh | ||
target_dec_fuzzer.c | ||
target_dem_fuzzer.c | ||
trasher.c | ||
uncoded_frame.c | ||
unwrap-diff | ||
yuvcmp.c | ||
zmqsend.c | ||
zmqshell.py |